Graded Quiz: Data Wrangling :Data Analysis with Python (IBM Data Analyst Professional Certificate) Answers 2025

1. Question 1

Method to replace missing values for continuous attributes:

• ❌ Educated guess

• ❌ Mean square error

• ❌ Min–max difference

• ✅ Use the average of the other values in the column

Explanation:

For continuous variables, the most common imputation method is using the mean (average).

2. Question 2

First step when deciding bin values for continuous data:

• ❌ Divide average by standard deviation

• ✅ Visualize the distribution (e.g., histogram)

• ❌ Convert object types

• ❌ Use IQR

Explanation:

You must first understand the distribution before creating bins.

3. Question 3

Most appropriate data type for city names like “N.Y.”, “Ny”, “New York”:

• ✅ object

• ❌ float

• ❌ DataFrame

• ❌ int

Explanation:

Non-numeric text values in Pandas are stored as object type.

4. Question 4

Primary purpose of normalization:

• ❌ Make all features identical

• ❌ Remove outliers

• ✅ Ensure features have similar ranges for fair comparison

• ❌ Remove missing values

Explanation:

Normalization adjusts scale, preventing large-range features from dominating.

5. Question 5

Converting categorical values into numerical values:

• ❌ Convert numerical to categorical

• ✅ Turns categorical values into numerical values

• ❌ Bin values

• ❌ Change data type manually

Explanation:

Encoding transforms categories into machine-learning friendly numbers.

6. Question 6

First step in data preparation:

• ✅ Cleaning missing or inconsistent values

• ❌ Normalizing values

• ❌ Running ML models

• ❌ Encoding categorical variables

Explanation:

Cleaning always comes first to ensure data reliability.

7. Question 7

Prepare “fuel type” column (gas/diesel) for model training:

• ❌ cut()

• ✅ get_dummies()

• ❌ dropna()

• ❌ astype()

Explanation:

get_dummies() performs one-hot encoding for categorical variables.

8. Question 8

Convert “N/A” text entries into actual NaN values:

• ✅ replace()

• ❌ astype()

• ❌ dropna()

• ❌ fillna()

Explanation:

Use replace("N/A", np.nan) to convert string placeholders to true missing values.

🧾 Summary Table